INDEX

Explanations

terms associated with breaking or altering connections and relationships

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 McIntosh

-0.71

ificance

-0.69

//});

-0.67

%</

-0.67

Yoo

-0.66

ahuila

-0.66

tamount

-0.64

`;

-0.64

Carcinogenicity

-0.61

❋

-0.61

POSITIVE LOGITS

 breaking

1.95

 Breaking

1.79

 broke

1.76

 break

1.75

Breaking

1.74

 broken

1.73

 BREAK

1.69

 breaks

1.68

break

1.67

breaking

1.66

Activations Density 0.127%

terms associated with breaking or altering connections and relationships

No Comments

No Known Activations